DeepForest

Detects individual tree crowns in aerial RGB imagery

Field
Forestry & vegetation
Method
Deep learning
Data it takes
imagery
License
MIT

DeepForest detects individual tree crowns in overhead RGB imagery, returning bounding boxes. It ships pretrained on NEON airborne data, so temperate forest imagery can be processed without additional labeling. Other canopy types generally require fine-tuning.

It suits projects with drone or aerial photography but no lidar.

Upstream project →

Catalog entry last checked 2026-08-17. All models →

Run DeepForest on your data

The lab runs this on its own compute, in a container, with the inputs and parameters recorded alongside the result. Initial scoping conversations are free.

Contact the Lab